Abstract: The disclosed concepts relate to employing agent behavior models to control agent behavior in an application, such as a video game or a simulation. For instance, in some implementations, agent behavior models with relatively greater resource utilization, such as generative language models, are assigned to agents that are at higher levels of an agent hierarchy. Agent behavior models with relatively less resource utilization, such as reinforcement learning or hard-coded models, are assigned to agents that are at lower levels of the agent hierarchy.

Abstract: Systems and methods are directed to generating content that is contextually relevant in a writing style of a user. In example embodiments, a plurality of logical inputs regarding a topic is received in bullet point format. A content generator generates draft content using machine learning (ML) models. The generating comprises identifying a writing style of the user by applying the plurality of logical inputs to a first ML model, determining a context and direction for the draft content using a second ML model, and based on the plurality of logical inputs, the identified writing style, and the context and direction, generating at least one paragraph of draft content in the writing style of the user that follows an outline associated with the bullet point format and comprises a same context and direction as the plurality of logical inputs. The draft content is then presented at a client device.

Abstract: Systems and methods are directed to generating content that is contextually relevant in a writing style of a user. In example embodiments, a plurality of logical inputs regarding a topic is received in bullet point format. A content generator generates draft content using machine learning (ML) models. The generating comprises identifying a writing style of the user by applying the plurality of logical inputs to a first ML model, determining a context and direction for the draft content using a second ML model, and based on the plurality of logical inputs, the identified writing style, and the context and direction, generating at least one paragraph of draft content in the writing style of the user that follows an outline associated with the bullet point format and comprises a same context and direction as the plurality of logical inputs. The draft content is then presented at a client device.

Abstract: A processing system is described which generates stimulus information (SI) having one or more stimulus components (SCs) selected from an inventory of such components. The processing system then presents the SI to a group of human recipients, inviting those recipients to provide linguistic descriptions of the SI. The linguistic information that is received thereby has an implicit link to the SCs. Further, each linguistic component is associated with at least one feature of a target environment, such as a target computer system. Hence, the linguistic information also maps to the features of the target environment. These relationships allow applications to use the linguistic information to interact with the target environment in different ways. In one case, the processing system uses a challenge-response authentication task presentation to convey the stimulus information to the recipients.

Abstract: A processing system is described which generates stimulus information (SI) having one or more stimulus components (SCs) selected from an inventory of such components. The processing system then presents the SI to a group of human recipients, inviting those recipients to provide linguistic descriptions of the SI. The linguistic information that is received thereby has an implicit link to the SCs. Further, each linguistic component is associated with at least one feature of a target environment, such as a target computer system. Hence, the linguistic information also maps to the features of the target environment. These relationships allow applications to use the linguistic information to interact with the target environment in different ways. In one case, the processing system uses a challenge-response authentication task presentation to convey the stimulus information to the recipients.

Abstract: A mining system applies queries to retrieve result items from an unstructured resource. The unstructured resource may correspond to a repository of network-accessible resource items. The result items that are retrieved may correspond to text segments (e.g., sentence fragments) associated with resource items. The mining system produces a structured training set by filtering the result items and establishing respective pairs of result items. A training system can use the training set to produce a statistical translation model. The translation model can be used in a monolingual context to translate between semantically-related phrases in a single language. The translation model can also be used in a bilingual context to translate between phrases expressed in two respective languages. Various applications of the translation model are also described.

Abstract: The present invention obtains a set of text segments from a cluster of different articles written about a common event. The set of text segments is then subjected to textual alignment techniques to identify paraphrases from the text segments in the text. The invention can also be used to generate paraphrases.

Abstract: Embodiments of the present invention provide a method and apparatus for segmenting text by providing orthographic and inflectional variations to a syntactic parser. Under the present invention, possible segments are first identified in the sequence of characters. At least two of the identified segments overlap each other. For at least one of the segments, an alternative sequence of characters is identified. In some cases, this alternative sequence is formed through inflectional morphology, which identifies a different lexical form for a word identified by the segment. In some cases, the alternative sequence represents an orthographic variant of a word identified by the segment. The identified segments and the alternative segments are then passed to a syntactic analyzer, which produces one or more syntactic parses. The segments found in the resulting parses represent the segmentation of the input sequence of characters.

Abstract: A lattice data structure suitable for storage on a computer-readable medium is provided which represents a plurality of orthographic forms of a Japanese lexical entry. The lattice includes a plurality of data fields each adapted to hold data representing a word element of the entry. Each data field includes a first subfield containing data representing a primary form of the corresponding word element and a second field containing data representing an alternate form of the corresponding word element. Also provided is a method of normalizing Japanese lexical entries to produce a normalized form that includes the primary form of each word-element representation of the lattice and does not include the alternate forms. Also provided are methods of segmenting text using the disclosed lattice.